semantic-segmentation
语义分割技能 - DeepLabV3、UNet、SegFormer ROS2 部署
语义分割技能 - DeepLabV3、UNet、SegFormer ROS2 部署
Use when implementing any feature, adding code, or modifying existing code in this Kotlin/Spring project. Triggers on write operations like adding entities, services, facades, controllers, or any domain logic.
ROS2 组件技能 - Composable Nodes、组件加载器、组件容器、跨进程通讯
Jetson ROS2集成 - v4l2_camera isaac_ros 机器人框架
OpenCV4 NVIDIA Jetson 部署技能 - Jetson Nano/Xavier/Orin、JetPack、CUDA、TensorRT、DLA
OpenCV4 Rockchip RKNN 部署技能 - RK3588/RK3399Pro、RKNN-Toolkit2、NPU 加速
Discover available plugins and generate 1-N execution proposals for a workflow structure. Each proposal is a complete WorkflowDefinition with executor config on every step.
瑞芯微RKNN模型转换 - ONNX PyTorch TensorFlow转RKNN
Django framework patterns, best practices, and implementation guides
.NET Core/ASP.NET patterns, best practices, and implementation guides
Laravel framework patterns, best practices, and implementation guides
NestJS framework patterns, best practices, and implementation guides
Ruby on Rails framework patterns, best practices, and implementation guides
Secondary local LLM inference engine via llama.cpp. This skill should be used when running GGUF models directly, loading LoRA adapters for Kothar, benchmarking inference speed, or serving models via llama-server. Includes dedicated Qwen 3.5 serve scripts (9B dense with F16 option, 35B MoE) with asymmetric KV cache and thinking mode. Complements Ollama (which remains primary for RLAMA and general use).
Invoke registered UDFs within Cypher queries using LibraryName.FunctionName() syntax
Implement policy as code with OPA, Sentinel, and Kyverno. Automate policy enforcement in CI/CD and infrastructure. Use when enforcing compliance through automation.
Implement typed error handling in Effect using Data.TaggedError, catchTag/catchTags, and recovery patterns. Use this skill when working with Effect error channels, handling expected failures, or designing error recovery strategies.